Scheduling, distributing and combining method and system for physical resources in cloud scene

Abstract

The invention discloses a scheduling, distributing and combining method and system for physical resources in cloud scene, and the method comprises the following steps: obtaining resource request data, and generating resource request object data, physical node data and distribution quantity data according to the processing of the resource request data; obtaining resource candidate data of the resource request object data from a resource database according to resource specification requirements in the resource request object data, and filling the resource request object data with the resource candidate data; combining the resource candidate data according to the physical node data to obtain a resource allocation list; and obtaining a corresponding amount of distribution data from a resource distribution list according to the distribution amount data. The system comprises a client, a server and a resource database, the server comprises a resource request analysis module, a resource candidate screening module, a resource candidate combinatorial algorithm module and an integration result processing module, the problems of time consumption and non-uniformity in allocation and acquisition under a large number of equipment scenes can be solved, and the effects of second-level return and uniform results are achieved.

Description

technical field [0001] The present invention relates to the field of scheduling, allocation and combination of physical resources, in particular to a method and system for scheduling, allocation and combination of physical resources in a cloud scene. Background technique [0002] In the field of cloud computing, a core requirement is to create a virtual machine. There are a large number of heterogeneous devices on a physical machine, including physical network cards, physical graphics cards and other devices. When creating a virtual machine, you need to select any number and type of heterogeneous How to select a suitable device combination among a large number of devices is a difficult problem, and these device combinations need to meet certain requirements; most of the current cloud environments do not contain a large number of physical devices, and its scheduling algorithm It is difficult to meet the scheduling requirements in a large number of physical equipment environme...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is that most of the current cloud environments do not contain a large number of physical devices, and its scheduling algorithm is difficult to meet the scheduling requirements in a large number of physical device environments. Suppose there are 200 physical machines, and each physical machine has There are 100 physical network cards and 100 graphics cards, among which a virtual machine needs 5 physical network cards and 5 physical graphics cards. Considering the requirements of various devices, it is currently impossible to choose a suitable device, and it is impossible to provide a large number of physical devices for The virtual machine selects a suitable combination. The present invention provides a method for scheduling, allocating and combining physical resources in a cloud scenario. The present invention also provides a system for scheduling, allocating and combining physical resources in a cloud. It can solve the problem of allocation in a large number of equipment scenarios Obtaining time-consuming and uneven problems has achieved the effect of returning in seconds, not taking up a lot of performance, and achieving uniform results, so as to solve the defects caused by existing technologies

Images